Abstract
the use of internet has increased exponentially. Search engines have become most important tool to retrieve any kind of information from the web. Users simply cast their queries on a search engine to get the desired information. More than thousands of documents are shown in search results of a query. Many times most of these web pages are not relevant to the user at all. Thus, it becomes essential for search engines to return only the relevant information to the user based on the query. Clustering makes it easier to separate out relevant results out of thousands of search results obtained for a query. Combining clustering with ranking can make it better as clustering makes groups of similar documents and applying ranking methods ranks each cluster according to their relevance with the user query. In this survey, various clustering techniques implemented before and their results are discussed. Some recent techniques discussed here are proven much more accurate than the traditional techniques.